Evaluate gene sets by cell type-specific gene expression

Setup

Load R libraries

library(data.table)
library(ggplot2)
library(ggpubr)
library(tidyr)
library(limma)
library(stringr)

theme_set(theme_classic())

Check enrichment of gene sets

Read in gene info and gene set assignments

assayed_genes = scan("output/gene_list_CD8T.txt", 
                     what = character(), sep="\n")

gene_sets = scan("output/name_s_CD8T.txt", 
                 what = character(), sep="\n")

gene_sets = sapply(gene_sets, strsplit, split=",")
n_genes   = sapply(gene_sets, length)
names(n_genes) = NULL
summary(n_genes)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00   10.75   16.00   14.47   19.00   22.00

length(n_genes)

## [1] 32

sort(n_genes)

##  [1]  1  4  8  9 10 10 10 10 11 11 11 12 12 13 15 16 16 17 17 17 18 18 18 19 19
## [26] 19 19 19 20 21 21 22

Find gene symbols using the alias2Symbol function from limma.

a2s = rep(NA, length(assayed_genes))
for(i in 1:length(assayed_genes)){
  gi = assayed_genes[i]
  ai = alias2Symbol(gi)
  if(length(ai) > 1){
    print(gi)
    print(ai)
  }
  a2s[i] = ai[1]
}

## [1] "MARS"
## [1] "MARS1" "SLA2" 
## [1] "QARS"
## [1] "EPRS1" "QARS1"
## [1] "APITD1"
## [1] "CENPS-CORT" "CENPS"     
## [1] "HIST1H2BC"
## [1] "H2BC5" "H2BC4"
## [1] "AIM1"
## [1] "CRYBG1"  "SLC45A2" "AURKB"

table(is.na(a2s))

## 
## FALSE  TRUE 
##  1169   155

table(a2s == assayed_genes, useNA = 'ifany')

## 
## FALSE  TRUE  <NA> 
##    70  1099   155

gene_info = data.table(sym_in_data = assayed_genes, sym_limma = a2s)

gene_info[sym_in_data != sym_limma,]

##     sym_in_data  sym_limma
##  1:       ZNRD1     POLR1H
##  2:      PPAP2A      PLPP1
##  3:      IMPAD1      BPNT2
##  4:      FAM45A    DENND10
##  5:    C6orf203     MTRES1
##  6:      HRSP12       RIDA
##  7:       FOPNL      CEP20
##  8:        WARS      WARS1
##  9:      CIRH1A       UTP4
## 10:      RRNAD1   METTL25B
## 11:      WDYHV1      NTAQ1
## 12:   HIST1H2BD      H2BC5
## 13:      AGPAT6      GPAT4
## 14:    C1orf123       CZIB
## 15:     TMEM155     SMIM43
## 16:        MARS      MARS1
## 17:      ENTHD2     TEPSIN
## 18:      FAM57A     TLCD3A
## 19:   HIST1H2AE      H2AC8
## 20:        QARS      EPRS1
## 21:      APITD1 CENPS-CORT
## 22:     CCDC101      SGF29
## 23:       PDDC1      GATD1
## 24:     EFCAB4A    CRACR2B
## 25:      CCDC23       SVBP
## 26:     EIF2S3L    EIF2S3B
## 27:   HIST1H2BC      H2BC5
## 28:         WRB       GET1
## 29:    TMEM194B      NEMP2
## 30:   KIAA0895L    MATCAP1
## 31:    HIST1H4C       H4C3
## 32:    HIST1H4J      H4C11
## 33:      ZNF720     KRBOX5
## 34:      FAM49A      CYRIA
## 35:  FLVCR1-AS1  FLVCR1-DT
## 36:    C1orf228      ARMH1
## 37:       TTC37      SKIC3
## 38:    C9orf114     SPOUT1
## 39:  HIST2H2AA4     H2AC19
## 40:   HIST2H2BF     H2BC18
## 41:   C10orf128    TMEM273
## 42:      SKIV2L      SKIC2
## 43:    RNVU1-13   RNVU1-19
## 44:    TCTEX1D2    DYNLT2B
## 45:    C17orf89    NDUFAF8
## 46:       PHBP3     PHB1P3
## 47:     SEPT7P7  SEPTIN7P7
## 48:   HIST1H2BN     H2BC15
## 49:       H2BFS    H2BC12L
## 50:     CASC4P1    GOLM2P1
## 51:   LINC00925   MIR9-3HG
## 52:    HIST1H3G       H3C8
## 53:      KLRAP1     KLRA1P
## 54:    EFTUD1P1     EFL1P1
## 55:    ATP5A1P3  ATP5F1AP3
## 56:    CCDC109B       MCUB
## 57:      ERO1LB      ERO1B
## 58:        AIM1     CRYBG1
## 59:        SELK    SELENOK
## 60:     C1orf63      RSRP1
## 61:      TMEM66      SARAF
## 62:       TMEM2     CEMIP2
## 63:      PCNXL2      PCNX2
## 64:        ACRC       GCNA
## 65:      PRMT10      PRMT9
## 66:     FAM102A      EEIG1
## 67:        SELM    SELENOM
## 68:      TMEM57      MACO1
## 69:   MKLN1-AS1  LINC-PINT
## 70:      RPL9P9     RPL9P8
##     sym_in_data  sym_limma

gene_info[, gene_symbol := sym_in_data]
gene_info[which(sym_in_data != sym_limma), 
                gene_symbol := sym_limma]

dim(gene_info)

## [1] 1324    3

gene_info[1:5,]

##    sym_in_data sym_limma gene_symbol
## 1:         FGR       FGR         FGR
## 2:      ANKIB1    ANKIB1      ANKIB1
## 3:      MAD1L1    MAD1L1      MAD1L1
## 4:        ICA1      ICA1        ICA1
## 5:     NDUFAF7   NDUFAF7     NDUFAF7

t1 = table(gene_info$gene_symbol)
table(t1)

## t1
##    1    2 
## 1320    2

gene_info[gene_symbol %in% names(t1)[t1 > 1],]

##    sym_in_data sym_limma gene_symbol
## 1:   HIST1H2BD     H2BC5       H2BC5
## 2:   HIST1H2BC     H2BC5       H2BC5
## 3:      RPL9P8    RPL9P8      RPL9P8
## 4:      RPL9P9    RPL9P8      RPL9P8

gene_info[sym_in_data == "HIST1H2BC", gene_symbol:="H2BC4"]
gene_info[sym_in_data == "HIST1H2BE", gene_symbol:="H2BC6"]
gene_info[sym_in_data == "RPL9P9", gene_symbol:="RPL9P9"]

Read in cell type-specific expression data

Gene set annotations (by gene symbols) were downloaded from MSigDB website.

ct = fread("../Annotation/rna_single_cell_type.tsv.gz")
dim(ct)

## [1] 1587110       4

ct[1:5,]

##               Gene Gene name             Cell type  nTPM
## 1: ENSG00000000003    TSPAN6            Adipocytes 149.5
## 2: ENSG00000000003    TSPAN6 Alveolar cells type 1   6.1
## 3: ENSG00000000003    TSPAN6 Alveolar cells type 2  10.5
## 4: ENSG00000000003    TSPAN6            Astrocytes  13.9
## 5: ENSG00000000003    TSPAN6               B-cells   1.5

length(unique(ct$`Cell type`))

## [1] 79

table(ct$`Cell type`)

## 
##                      Adipocytes           Alveolar cells type 1 
##                           20090                           20090 
##           Alveolar cells type 2                      Astrocytes 
##                           20090                           20090 
##                         B-cells             Basal keratinocytes 
##                           20090                           20090 
##           Basal prostatic cells         Basal respiratory cells 
##                           20090                           20090 
## Basal squamous epithelial cells                   Bipolar cells 
##                           20090                           20090 
##          Breast glandular cells      Breast myoepithelial cells 
##                           20090                           20090 
##                  Cardiomyocytes                  Cholangiocytes 
##                           20090                           20090 
##                      Club cells           Collecting duct cells 
##                           20090                           20090 
##        Cone photoreceptor cells                Cytotrophoblasts 
##                           20090                           20090 
##                 dendritic cells              Distal enterocytes 
##                           20090                           20090 
##            Distal tubular cells                    Ductal cells 
##                           20090                           20090 
##                Early spermatids      Endometrial ciliated cells 
##                           20090                           20090 
##       Endometrial stromal cells               Endothelial cells 
##                           20090                           20090 
##           Enteroendocrine cells                 Erythroid cells 
##                           20090                           20090 
##              Excitatory neurons        Exocrine glandular cells 
##                           20090                           20090 
##       Extravillous trophoblasts                     Fibroblasts 
##                           20090                           20090 
##   Gastric mucus-secreting cells     Glandular and luminal cells 
##                           20090                           20090 
##                    granulocytes                 Granulosa cells 
##                           20090                           20090 
##                     Hepatocytes                  Hofbauer cells 
##                           20090                           20090 
##                Horizontal cells              Inhibitory neurons 
##                           20090                           20090 
##         Intestinal goblet cells                       Ionocytes 
##                           20090                           20090 
##                   Kupffer cells                Langerhans cells 
##                           20090                           20090 
##                 Late spermatids                    Leydig cells 
##                           20090                           20090 
##                     Macrophages                     Melanocytes 
##                           20090                           20090 
##                Microglial cells                       monocytes 
##                           20090                           20090 
##           Mucus glandular cells               Muller glia cells 
##                           20090                           20090 
##                        NK-cells Oligodendrocyte precursor cells 
##                           20090                           20090 
##                Oligodendrocytes      Pancreatic endocrine cells 
##                           20090                           20090 
##                    Paneth cells               Peritubular cells 
##                           20090                           20090 
##                    Plasma cells       Prostatic glandular cells 
##                           20090                           20090 
##            Proximal enterocytes          Proximal tubular cells 
##                           20090                           20090 
##      Respiratory ciliated cells         Rod photoreceptor cells 
##                           20090                           20090 
##             Salivary duct cells                   Schwann cells 
##                           20090                           20090 
##          Serous glandular cells                   Sertoli cells 
##                           20090                           20090 
##               Skeletal myocytes             Smooth muscle cells 
##                           20090                           20090 
##                   Spermatocytes                   Spermatogonia 
##                           20090                           20090 
##       Squamous epithelial cells        Suprabasal keratinocytes 
##                           20090                           20090 
##            Syncytiotrophoblasts                         T-cells 
##                           20090                           20090 
##                     Theca cells         Thymic epithelial cells 
##                           20090                           20090 
##          Undifferentiated cells 
##                           20090

ct_immune = fread("../Annotation/rna_immune_cell_monaco.tsv.gz")
dim(ct_immune)

## [1] 602700      5

ct_immune[1:5,]

##               Gene Gene name                Immune cell TPM pTPM
## 1: ENSG00000000003    TSPAN6                   basophil  NA  1.2
## 2: ENSG00000000003    TSPAN6  Central memory CD8 T-cell  NA  1.7
## 3: ENSG00000000003    TSPAN6         classical monocyte  NA  0.2
## 4: ENSG00000000003    TSPAN6 Effector memory CD8 T-cell  NA  0.7
## 5: ENSG00000000003    TSPAN6    Exhausted memory B-cell  NA  0.7

summary(ct_immune$TPM)

##    Mode    NA's 
## logical  602700

summary(ct_immune$pTPM)

##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##     0.00     0.00     3.10    49.74    27.20 96572.50

summary(ct_immune$pTPM[ct_immune$pTPM > 0])

##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##     0.10     1.70    11.60    67.96    42.80 96572.50

length(unique(ct_immune$`Immune cell`))

## [1] 30

table(ct_immune$`Immune cell`)

## 
##                            basophil           Central memory CD8 T-cell 
##                               20090                               20090 
##                  classical monocyte          Effector memory CD8 T-cell 
##                               20090                               20090 
##             Exhausted memory B-cell               intermediate monocyte 
##                               20090                               20090 
##                         MAIT T-cell               Memory CD4 T-cell TFH 
##                               20090                               20090 
##               Memory CD4 T-cell Th1          Memory CD4 T-cell Th1/Th17 
##                               20090                               20090 
##              Memory CD4 T-cell Th17               Memory CD4 T-cell Th2 
##                               20090                               20090 
##                          myeloid DC                        naive B-cell 
##                               20090                               20090 
##                    naive CD4 T-cell                    naive CD8 T-cell 
##                               20090                               20090 
##                          neutrophil                             NK-cell 
##                               20090                               20090 
##              non-classical monocyte          Non-switched memory B-cell 
##                               20090                               20090 
##                       Non-Vd2 gdTCR                         Plasmablast 
##                               20090                               20090 
##                     plasmacytoid DC                     Progenitor cell 
##                               20090                               20090 
##              Switched memory B-cell                               T-reg 
##                               20090                               20090 
## Terminal effector memory CD4 T-cell Terminal effector memory CD8 T-cell 
##                               20090                               20090 
##                          total PBMC                           Vd2 gdTCR 
##                               20090                               20090

lineage = fread("../Annotation/rna_immune_cell_monaco_cell_types.tsv")
dim(lineage)

## [1] 30  2

lineage[1:2,]

##     Cell_type      Lineage
## 1:   Basophil Granulocytes
## 2: Neutrophil Granulocytes

Check gene expression for each gene set

dim(gene_info)

## [1] 1324    3

for(k in 1:length(gene_sets)){
  if(length(gene_sets[[k]]) < 5) { next }
  
  print(k)
  set_k = paste0("set_", k)
  print(gene_sets[[k]])
  
  genes = gene_info[sym_in_data %in% gene_sets[[k]], gene_symbol]

  n_genes = sum(genes %in% ct_immune$`Gene name`)
  print(sprintf("found %d genes.", n_genes))

  if(n_genes == 0) { next }

  df = ct_immune[`Gene name` %in% genes,]
  dim(df)
  df[1:2,]
  
  stopifnot(all(str_to_lower(df$`Immune cell`) %in% 
                  str_to_lower(lineage$Cell_type)))
  
  mat1 = match(str_to_lower(df$`Immune cell`), 
               str_to_lower(lineage$Cell_type))
  
  df = cbind(df, lineage[mat1,])
  df[1:2,]
  
  df$Cell_type = factor(df$Cell_type, levels = lineage$Cell_type)
  df = df[df$Lineage != "Total PBMC",]
  df$Lineage   = factor(df$Lineage, 
                        levels = setdiff(lineage$Lineage, "Total PBMC"))
  
  p1 = ggplot(df, aes(x=Cell_type, y=log10(pTPM + 0.1), fill=Lineage)) + 
    geom_boxplot() + xlab("Cell type") + ggtitle(set_k) + 
    theme(axis.text.x = element_text(angle = 45, hjust = 1)) + 
    scale_fill_brewer(palette="RdBu")

  print(p1)
}

## [1] 1
##  [1] "SPATA6L"        "PDCD2L"         "MTO1"           "GPN2"          
##  [5] "FGD2"           "WRB"            "MSH5"           "LCAT"          
##  [9] "RP11-783K16.14" "RP11-493L12.4"  "RNU12"          "CTB-131B5.2"   
## [1] "found 8 genes."

## [1] 2
##  [1] "TIMM9"   "ABHD11"  "IFI44L"  "ATG16L2" "BPGM"    "BOLA1"   "CEP57L1"
##  [8] "HDDC3"   "MBD5"    "CCL3L1"  "PGAM4"  
## [1] "found 10 genes."

## [1] 3
##  [1] "GCFC2"        "SLC11A2"      "SCPEP1"       "FOPNL"        "ATF7IP2"     
##  [6] "MEI1"         "TMEM120A"     "ZNF511"       "PPIAP31"      "RP1-134E15.3"
## [11] "TPRG1"       
## [1] "found 9 genes."

## [1] 4
##  [1] "POLD3"         "TTLL1"         "REC8"          "CDADC1"       
##  [5] "NR2C1"         "TPGS2"         "CTSB"          "TBCA"         
##  [9] "RP1-20N2.6"    "RP11-446E9.1"  "RP11-335G20.7"
## [1] "found 8 genes."

## [1] 5
##  [1] "ZNF268"        "NSMCE4A"       "NDUFAF6"       "TMSB15B"      
##  [5] "CMAHP"         "ZNF561"        "CCDC23"        "ZNF799"       
##  [9] "ZNF257"        "AC098614.2"    "AC009403.2"    "SF3A3P2"      
## [13] "CTD-2555O16.4" "CTD-3092A11.1" "RP11-632K20.7" "RP1-68D18.2"  
## [1] "found 8 genes."

## [1] 6
##  [1] "C3orf14"        "MFSD9"          "SCRN2"          "XCL1"          
##  [5] "CCDC28B"        "DBF4B"          "GNGT2"          "DUS1L"         
##  [9] "NME6"           "DLGAP1-AS1"     "ENTPD5"         "ZNF720"        
## [13] "IGHV1-3"        "GUSBP9"         "AC093642.5"     "TRGC2"         
## [17] "RN7SL749P"      "RP11-1415C14.4" "RPS3AP26"      
## [1] "found 12 genes."

## [1] 7
##  [1] "RGS1"         "TEP1"         "IL10"         "IFI44"        "XRRA1"       
##  [6] "ZNF683"       "TRAV16"       "TRAV19"       "TRDV1"        "TRDC"        
## [11] "PATL2"        "PTGES3P1"     "TRBV3-1"      "RP3-395M20.8" "RP11-81H14.2"
## [16] "RP11-23J18.1" "AL161784.1"   "RP11-51J9.5" 
## [1] "found 12 genes."

## [1] 8
##  [1] "CRTAM"         "NUDT7"         "PLIN2"         "CXCR6"        
##  [5] "EFCAB4A"       "KIAA0895L"     "PDCL3P5"       "RPSAP54"      
##  [9] "RPL19P12"      "RP11-270C12.3" "MIR29B1"       "RP11-119F19.2"
## [13] "RPS11P5"       "RP11-288E14.2" "EEF1A1P10"     "YWHAQP6"      
## [17] "RP11-345J4.6"  "MIR142"       
## [1] "found 5 genes."

## [1] 9
##  [1] "CHI3L2"         "ZNF302"         "GMPR2"          "FAHD2A"        
##  [5] "KHDC1"          "ZFP14"          "GTSF1"          "FAM49A"        
##  [9] "C1orf228"       "CPT1B"          "RNU2-2P"        "RP11-109G10.2" 
## [13] "RP11-247I13.6"  "RP11-262H14.3"  "ETF1P2"         "RN7SL834P"     
## [17] "RP11-382J24.2"  "RP11-265N6.2"   "RP11-1399P15.1"
## [1] "found 10 genes."

## [1] 10
##  [1] "PMS2P3"         "ASNSD1"         "LRRC45"         "NAP1L4P1"      
##  [5] "GEN1"           "SLC36A4"        "ZNF749"         "TRGV10"        
##  [9] "LINC00630"      "ACTG1P10"       "CTD-2301A4.3"   "WDR86-AS1"     
## [13] "ZNF674"         "RP11-116B19.2"  "RPPH1"          "TRAV30"        
## [17] "AC006483.1"     "RP11-209D14.4"  "RP11-686D22.10" "TMEM256P2"     
## [1] "found 8 genes."

## [1] 11
##  [1] "ZNRD1"         "POLR2I"        "GALE"          "AKR1A1"       
##  [5] "TRPT1"         "GALK2"         "C1orf123"      "POLR2H"       
##  [9] "TMEM134"       "TREX1"         "RP11-33B1.1"   "CTD-2521M24.9"
## [1] "found 10 genes."

## [1] 12
##  [1] "ZNF85"         "CCRL2"         "RRNAD1"        "SPATA33"      
##  [5] "RP11-262H14.4" "CES2"          "ZNF93"         "ARHGAP11B"    
##  [9] "HIST1H4C"      "RP11-545E17.3" "RP11-305L7.3"  "FAM200B"      
## [13] "RP11-102M11.1" "TPM3P6"        "RP11-493L12.6" "AC004158.2"   
## [17] "EIF4BP5"      
## [1] "found 8 genes."

## [1] 13
##  [1] "G2E3"          "CHKB"          "ARMC2"         "CARF"         
##  [5] "B2M"           "ZNF28"         "TMSB4X"        "RNVU1-13"     
##  [9] "PIN4P1"        "LINC00925"     "RP11-467L13.4" "TIPARP"       
## [13] "TMEM116"       "AC021593.1"    "AC008440.5"    "MALAT1"       
## [1] "found 9 genes."

## [1] 14
##  [1] "TNFRSF9"      "ZNF585A"      "MGAT4A"       "TXK"          "TCF7"        
##  [6] "CCR7"         "NEK1"         "ACRC"         "FILIP1L"      "GPR183"      
## [11] "KRT86"        "ANKRD37"      "SELL"         "MIR4461"      "MTND1P23"    
## [16] "HCG4P5"       "RPL3P2"       "RP1-187B23.1" "HLA-W"        "RP11-747H7.3"
## [21] "SLC7A5P1"     "RP1-313I6.12"
## [1] "found 13 genes."

## [1] 15
## [1] "FOXP1"         "RPL21"         "AOAH"          "RPS14"        
## [5] "RP11-572P18.1" "RPL10P3"       "RPL9P8"        "RPL9P9"       
## [9] "CTD-2031P19.4"
## [1] "found 4 genes."

## [1] 16
##  [1] "TSPAN32"       "HPGD"          "KIR3DL1"       "NAALADL1"     
##  [5] "ZNF80"         "C10orf128"     "TRBV4-2"       "TRBV20-1"     
##  [9] "TRAV12-2"      "TRAV24"        "RPS19P1"       "RP3-340B19.5" 
## [13] "KIR2DS4"       "AC007041.2"    "RN7SL56P"      "RNU1-125P"    
## [17] "RP11-291B21.2" "RP11-304L19.5" "AC139149.1"   
## [1] "found 10 genes."

## [1] 17
##  [1] "MBNL3"      "GNLY"       "VPS8"       "ETFDH"      "SPIN2B"    
##  [6] "AC012318.3" "PPIL3"      "IER5"       "BTBD19"     "LINC00944" 
## [1] "found 8 genes."

## [1] 18
##  [1] "MS4A6A"        "SLC41A3"       "XCL2"          "NFKBIZ"       
##  [5] "MZT2A"         "SLC25A53"      "TCTEX1D2"      "RP4-742C19.12"
##  [9] "GS1-124K5.2"   "RP11-254B13.4" "RP11-693N9.2"  "AC092580.4"   
## [13] "CTB-4E7.1"     "USP30-AS1"     "HMBS"          "CCL3L3"       
## [17] "RP11-705C15.5"
## [1] "found 9 genes."

## [1] 19
##  [1] "AKAP10"        "PUS7L"         "NTAN1"         "EIF2S3L"      
##  [5] "ZNF559"        "HIST1H4J"      "METTL6"        "RNVU1-14"     
##  [9] "TRGV8"         "TRGV5"         "RPL5P5"        "PSMA6P1"      
## [13] "MAPKAPK5-AS1"  "LINC00426"     "RP11-416A17.6" "RP11-713N11.3"
## [17] "RP3-508I15.20"
## [1] "found 9 genes."

## [1] 20
##  [1] "CXCL13"       "ERO1LB"       "HECA"         "MAN1C1"       "PCNXL2"      
##  [6] "RASGEF1B"     "C1orf162"     "NR4A2"        "MPZL3"        "PLXDC1"      
## [11] "CDC42EP3"     "PRMT10"       "BCL9L"        "SELM"         "XIST"        
## [16] "RPL9P7"       "RP11-285F7.2" "PLA2G4B"      "ZNF10"        "QRSL1P3"     
## [21] "KCNQ1OT1"    
## [1] "found 16 genes."

## [1] 21
##  [1] "DYRK4"       "HPS4"        "FGFBP2"      "DRAM2"       "CX3CR1"     
##  [6] "ADPRM"       "HARBI1"      "FCRL6"       "EFCAB7"      "TRAV14DV4"  
## [11] "KANSL1-AS1"  "RP11-2F9.3"  "AC090804.1"  "RP4-728D4.2" "ZBTB20-AS1" 
## [16] "TRAV1-2"     "KLRAP1"      "NPM1P5"      "PLAC8"      
## [1] "found 12 genes."

## [1] 22
##  [1] "RP3-324O17.4" "NHP2P1"       "MDGA1"        "DTD2"         "ZBTB8OSP2"   
##  [6] "RPS2P4"       "FLVCR1-AS1"   "TRAV8-2"      "RP11-12M9.4"  "RSC1A1"      
## [11] "RP4-800M22.1" "RP3-342P20.2" "PRDX3P1"      "PA2G4P4"      "SNRPEP4"     
## [16] "ADH5P4"       "Z97634.3"     "RP11-32B5.1"  "RP11-90P5.2"  "HMGB1P24"    
## [21] "MIR3661"     
## [1] "found 4 genes."

## [1] 23
##  [1] "OAS1"     "ELMOD3"   "RSAD2"    "TMEM138"  "ISG20"    "TMEM194B"
##  [7] "CRYZL1"   "TSTD1"    "PTGES3P2" "TSC22D3" 
## [1] "found 9 genes."

## [1] 24
##  [1] "VPS41"      "GALK1"      "STYXL1"     "FUOM"       "TECPR1"    
##  [6] "TRAV8-3"    "RNU2-63P"   "TRGV2"      "AC144530.1" "PVT1"      
## [11] "AC013269.1" "CPQ"        "HS6ST1"    
## [1] "found 9 genes."

## [1] 25
##  [1] "IFI27"         "RPL21P8"       "WDR53"         "TRAV35"       
##  [5] "RP4-694B14.5"  "RP11-247I13.3" "CALM2P3"       "RP1-182O16.1" 
##  [9] "CTA-217C2.1"   "RP11-381O7.6"  "AC147651.4"    "AP000476.1"   
## [13] "RP11-168J18.6" "KB-1507C5.2"   "TRAV1-1"       "RP11-613F22.5"
## [17] "CTB-31O20.3"   "CTD-3214H19.4" "RP11-297D21.4"
## [1] "found 3 genes."

## [1] 26
##  [1] "TM7SF3"        "ADAT1"         "WDR91"         "C12orf57"     
##  [5] "FAM45A"        "SLC37A3"       "TNFRSF18"      "TRBV9"        
##  [9] "TRAV13-1"      "RP11-773D16.1" "SKP1P1"        "INSL3"        
## [13] "TRGV7"         "SNORD3A"       "FAM102A"      
## [1] "found 10 genes."

## [1] 27
##  [1] "ICA1"          "ERMARD"        "RNF207"        "TNFAIP8L2"    
##  [5] "CADM1"         "TRAV29DV5"     "UBA52P6"       "ARPC3P1"      
##  [9] "ZNF826P"       "RP5-1099D15.1" "SNRPGP10"      "BHLHE40-AS1"  
## [13] "RP11-712B9.2"  "AP000462.1"    "RP11-638I2.10" "RP11-1012A1.7"
## [17] "AC006129.4"    "ARL4A"        
## [1] "found 7 genes."

## [1] 28
##  [1] "ANKIB1"       "TMEM66"       "NPIPB3"       "NPIPB4"       "MTND2P28"    
##  [6] "CTD-2328D6.1" "NPIPB5"       "MTATP6P1"     "RP11-72I8.1"  "RP11-78A19.3"
## [1] "found 5 genes."

## [1] 31
## [1] "RAD51C"  "STMN1"   "TXNDC17" "TMEM155" "WEE1"    "UBE2C"   "TYMS"   
## [8] "SESTD1" 
## [1] "found 8 genes."

## [1] 32
##  [1] "CD84"          "TRANK1"        "SH2D1B"        "PET100"       
##  [5] "AC104820.2"    "STAT4"         "FAM177A1"      "MKLN1-AS1"    
##  [9] "RP11-373L24.1" "RP11-138A9.2" 
## [1] "found 6 genes."

Session information

gc()

##            used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
## Ncells  4141885 221.3    8075322 431.3         NA  8075322 431.3
## Vcells 20538860 156.7   35549985 271.3      65536 29492531 225.1

sessionInfo()

## R version 4.2.3 (2023-03-15)
## Platform: aarch64-apple-darwin20 (64-bit)
## Running under: macOS Ventura 13.4.1
## 
## Matrix products: default
## BLAS:   /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/lib/libRlapack.dylib
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] stringr_1.5.0     limma_3.54.2      tidyr_1.3.0       ggpubr_0.6.0     
## [5] ggplot2_3.4.2     data.table_1.14.8
## 
## loaded via a namespace (and not attached):
##  [1] Rcpp_1.0.10            png_0.1-8              Biostrings_2.66.0     
##  [4] digest_0.6.31          utf8_1.2.3             R6_2.5.1              
##  [7] GenomeInfoDb_1.34.9    backports_1.4.1        stats4_4.2.3          
## [10] RSQLite_2.3.1          evaluate_0.20          httr_1.4.6            
## [13] pillar_1.9.0           zlibbioc_1.44.0        rlang_1.1.0           
## [16] rstudioapi_0.14        car_3.1-2              jquerylib_0.1.4       
## [19] blob_1.2.4             R.oo_1.25.0            R.utils_2.12.2        
## [22] S4Vectors_0.36.2       rmarkdown_2.21         labeling_0.4.2        
## [25] RCurl_1.98-1.12        bit_4.0.5              munsell_0.5.0         
## [28] broom_1.0.4            compiler_4.2.3         xfun_0.39             
## [31] pkgconfig_2.0.3        BiocGenerics_0.44.0    htmltools_0.5.5       
## [34] tidyselect_1.2.0       KEGGREST_1.38.0        GenomeInfoDbData_1.2.9
## [37] tibble_3.2.1           IRanges_2.32.0         fansi_1.0.4           
## [40] crayon_1.5.2           dplyr_1.1.2            withr_2.5.0           
## [43] R.methodsS3_1.8.2      bitops_1.0-7           grid_4.2.3            
## [46] jsonlite_1.8.4         gtable_0.3.3           lifecycle_1.0.3       
## [49] DBI_1.1.3              magrittr_2.0.3         scales_1.2.1          
## [52] cli_3.6.1              stringi_1.7.12         cachem_1.0.7          
## [55] carData_3.0-5          farver_2.1.1           XVector_0.38.0        
## [58] ggsignif_0.6.4         bslib_0.4.2            generics_0.1.3        
## [61] vctrs_0.6.2            RColorBrewer_1.1-3     org.Hs.eg.db_3.16.0   
## [64] tools_4.2.3            bit64_4.0.5            Biobase_2.58.0        
## [67] glue_1.6.2             purrr_1.0.1            abind_1.4-5           
## [70] fastmap_1.1.1          yaml_2.3.7             AnnotationDbi_1.60.2  
## [73] colorspace_2.1-0       rstatix_0.7.2          memoise_2.0.1         
## [76] knitr_1.44             sass_0.4.5